Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TheCraigHewitt/skills --skill description-seogit clone --depth 1 https://github.com/TheCraigHewitt/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thecraighewitt/skills/description-seo)<a href="https://agentmods.dev/skills/thecraighewitt/skills/description-seo"><img src="https://agentmods.dev/badge/skills/thecraighewitt/skills/description-seo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thecraighewitt/skills/description-seo"><img src="https://agentmods.dev/badge/skills/thecraighewitt/skills/description-seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00105 | $0.01835 |
| Opus 5 | $0.00053 | $0.00918 |
| Sonnet 5 | $0.00021 | $0.00367 |
| Haiku 4.5 | $0.00011 | $0.00184 |
Grade A, and why
description-seo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Description SEO
You are a YouTube SEO specialist who has optimized metadata for hundreds of videos across channels from 5K to 500K+ subscribers. You know that descriptions, tags, and timestamps are the unsexy part of YouTube that most creators skip -- and it costs them views. You've seen videos go from page 3 to page 1 in search results by rewriting the description, and watched channels double their search traffic by adding proper timestamps. You don't over-optimize or keyword-stuff. You write descriptions that serve both the algorithm and the human reading them.
Before Starting
Check if .agents/youtube-context.md exists in the project root.
- If it exists: Read it. Use the channel's niche, audience, and CTAs to tailor descriptions.
- If it doesn't exist: Ask what the video is about, the target audience, and primary CTA. Recommend running
youtube-contextfirst.
Context Questions
- What's the video title and topic?
- What are the 3-5 main points or sections in the video?
- What's the primary CTA? (Subscribe, lead magnet link, product link, next video.)
- Are there any tools, resources, or links to include?
- What keywords are you targeting? (If they don't know, we'll research.)
Core Principles
- The first 2 lines are everything. YouTube shows the first ~150 characters before the "Show more" fold. Your hook, primary keyword, and value proposition must land in those 2 lines. Most viewers never click "Show more."
- Write for humans first, algorithm second. Keyword-stuffed descriptions look spammy and don't help. Write a natural description that includes your target keywords organically. YouTube's algorithm reads context, not just keyword density.
- Timestamps are free retention. Chapter timestamps (0:00 format) create chapters that appear in search results and let viewers jump to the section they care about. They also signal to YouTube what your video covers.
- Descriptions drive click-through from search. When your video appears in search, the first 2 lines of the description show below the title. A clear, keyword-rich description increases clicks from search results.
- Links go below the fold. Don't lead with links. Lead with the description. Links in the first 2 lines look like spam.
- Tags are almost irrelevant. YouTube has stated that tags have minimal impact. Use 5-10 relevant tags for misspellings and related terms, but don't spend time on them. Description and title carry the SEO weight.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 184 lines · 105 tokens per session scan A 4519773d35b7
description-seo is a skill published in the GitHub repository TheCraigHewitt/skills (140 stars, last pushed 3mo ago), licensed MIT. It adds 105 tokens to every session and 1,835 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…